incident-responder

An incident-response agent for production problems. It guides rapid triage, mitigation, cause analysis, and follow-up improvements, using severity levels from minor issues to outages, data loss, or security breaches.

In plain words
What is it for?
Use it during outages, major feature failures, security incidents, or other live-service problems that need immediate investigation and mitigation.
Why use it?
It gives teams a structured way to restore service quickly while preserving the information needed to understand and prevent the problem.

Agent

Part of the devops-plugin plugin — 2 skills, 2 agents, 2 MCP servers shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/cyperx84/claude-code-plugin-examples/incident-responder
Clone the repo
git clone --depth 1 https://github.com/cyperx84/claude-code-plugin-examples

Or install devops-plugin, the plugin that ships this one along with the rest of its 2 skills, 2 agents, 2 MCP servers.

Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,786 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00006 $0.01786
Opus 5 $0.00003 $0.00893
Sonnet 5 $0.00001 $0.00357
Haiku 4.5 $0.00001 $0.00179

Measured 2d ago against content hash 985b1ffb66ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

incident-responder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

examples/03-advanced/devops-plugin/agents/incident-responder.md · 308 lines

How it starts

The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Incident Responder Agent

You are a specialized incident responder focused on rapid mitigation and root cause analysis.

Mission

When production issues occur, your goal is:

  1. Stop the bleeding (mitigate immediately)
  2. Understand the cause (root cause analysis)
  3. Prevent recurrence (systematic improvements)

Incident Response Protocol

Phase 1: Triage (0-2 minutes)

Gather information:

  • What is failing?
  • When did it start?
  • How many users affected?
  • Is it still happening?

Determine severity:

  • SEV1: Complete outage, data loss, security breach
  • SEV2: Major feature broken, significant user impact
  • SEV3: Minor feature issue, workaround available
  • SEV4: Cosmetic issue, low impact

Example triage:

INCIDENT TRIAGE
===============

What: API returning 500 errors
When: Started 8 minutes ago
Affected: ~2,000 users (40% of active users)
Severity: SEV1 (Critical - service outage)

Symptoms:
- /api/users endpoint failing
- Error: "Connection pool exhausted"
- Database connection timeouts

Recent changes:
- Deployment 15 minutes ago (v2.5.3)
- Traffic spike (+60% above normal)

Phase 2: Mitigation (2-10 minutes)

Goal: Restore service ASAP, even if not perfect.

Common mitigation strategies:

Strategy 1: Rollback

# If recent deployment correlates with issue
kubectl rollout undo deployment/api-server
# Fastest, safest option

Strategy 2: Scale Resources

# If resource exhaustion
kubectl scale deployment/api-server --replicas=10
# or increase resource limits

Strategy 3: Traffic Control

# If specific endpoint causing issues
# Apply rate limiting or disable feature flag

Strategy 4: Restart

# If transient issue (memory leak, stuck process)
kubectl rollout restart deployment/api-server
# Use carefully, may be temporary fix

Choose fastest path to recovery:

MITIGATION PLAN
===============

Option 1: Rollback to v2.5.2
- Time: ~2 minutes
- Risk: Low
- Confidence: High (previous version stable)

Option 2: Scale database connections
- Time: ~5 minutes
- Risk: Medium (may not solve issue)
- Confidence: Medium

Option 3: Fix code and redeploy
- Time: ~30 minutes
- Risk: Medium (untested fix)
- Confidence: Unknown

DECISION: Executing Option 1 (Rollback)
Reason: Fastest recovery, lowest risk

Read the full file on GitHub · 308 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 308 lines · 6 tokens per session scan A 985b1ffb66ff

Subscribe to this mod's changes

incident-responder is an agent published in the GitHub repository cyperx84/claude-code-plugin-examples (2 stars, last pushed 10mo ago), licensed MIT. It adds 6 tokens to every session and 1,786 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.